English
Related papers

Related papers: Differentiable Weighted Finite-State Transducers

200 papers

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we…

Computation and Language · Computer Science 2019-11-12 Guy Rotman , Roi Reichart

Deep neural networks are typically trained in a single shot for a specific task and data distribution, but in real world settings both the task and the domain of application can change. The problem becomes even more challenging in dense…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Donald Shenaj , Francesco Barbato , Umberto Michieli , Pietro Zanuttigh

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Chunmeng Liu , Enze Xie , Wenjia Wang , Wenhai Wang , Guangyao Li , Ping Luo

Recurrent Neural Networks (RNNs) have achieved tremendous success in sequential data processing. However, it is quite challenging to interpret and verify RNNs' behaviors directly. To this end, many efforts have been made to extract finite…

Computation and Language · Computer Science 2022-09-28 Zeming Wei , Xiyue Zhang , Meng Sun

We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to lattice re-scoring…

Computation and Language · Computer Science 2020-01-07 Kareem Nassar

Extracting finite state automata (FSAs) from black-box models offers a powerful approach to gaining interpretable insights into complex model behaviors. To support this pursuit, we present a weighted variant of Angluin's (1987)…

Computation and Language · Computer Science 2024-12-20 Clemente Pasti , Talu Karagöz , Anej Svete , Franz Nowak , Reda Boumasmoud , Ryan Cotterell

The need of interpreting Deep Learning (DL) models has led, during the past years, to a proliferation of works concerned by this issue. Among strategies which aim at shedding some light on how information is represented internally in DL…

Machine Learning · Computer Science 2020-04-02 Reda Marzouk , Colin de la Higuera

Segmented models are widely used to describe non-stationary sequential data with discrete change points. Their estimation usually requires solving a mixed discrete-continuous optimization problem, where the segmentation is the discrete part…

Machine Learning · Computer Science 2021-01-19 Erik Scharwächter , Jonathan Lennartz , Emmanuel Müller

Density Functional Theory (DFT) is widely used for first-principles simulations in chemistry and materials science, but its computational cost remains a key limitation for large systems. Motivated by recent advances in ML-based…

Materials Science · Physics 2026-02-19 Rakshit Kumar Singh , Aryan Amit Barsainyan , Bharath Ramsundar

In this paper, we present connections between three models used in different research fields: weighted finite automata~(WFA) from formal languages and linguistics, recurrent neural networks used in machine learning, and tensor networks…

Machine Learning · Computer Science 2022-01-10 Tianyu Li , Doina Precup , Guillaume Rabusseau

We show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early '90s, where a ``slow" neural net learns by gradient descent to program the ``fast weights" of another net through sequences of…

Machine Learning · Computer Science 2021-06-10 Imanol Schlag , Kazuki Irie , Jürgen Schmidhuber

In recent years, neural networks have proven to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired…

Computation and Language · Computer Science 2017-11-07 Jingjing Xu , Xu Sun , Sujian Li , Xiaoyan Cai , Bingzhen Wei

Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progress w.r.t. the mean Intersection-over Union (mIoU) with the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Xiaofeng Liu , Yimeng Zhang , Xiongchang Liu , Song Bai , Site Li , Jane You

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they…

Computation and Language · Computer Science 2023-06-06 Xiaoyue Wang , Lijie Wang , Xin Liu , Suhang Wu , Jinsong Su , Hua Wu

We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…

Machine Learning · Statistics 2021-08-17 Dino Oglic , Zoran Cvetkovic , Peter Sollich

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Text classification plays an important role in many practical applications. In the real world, there are extremely small datasets. Most existing methods adopt pre-trained neural network models to handle this kind of dataset. However, these…

Computation and Language · Computer Science 2022-06-27 Jiajun Tong , Zhixiao Wang , Xiaobin Rui

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT…

Machine Learning · Computer Science 2019-11-11 Jonathan Lorraine , Paul Vicol , David Duvenaud